osmos::feed

Open

Grounding Foundation Models through Federated Transfer Learning: A General Framework. (arXiv:2311.17431v6 [cs.LG] UPDATED)

Foundation Models (FMs) such as GPT-4 encoded with vast knowledge and powerful emergent abilities have achieved remarkable success in various natural language processing and computer vision tasks. Grounding FMs by adapting them to domain-specific tasks or augmenting them with domain-specific knowledge enables us to exploit the full potential of FMs. However, grounding FMs faces several challenges, stemming primarily from constrained computing resources, data privacy, model heterogeneity, and model ownership. Federated Transfer Learning (FTL), the combination of federated learning and transfer learning, provides promising solutions to address these challenges. In recent years, the need for grounding FMs leveraging FTL, coined FTL-FM, has arisen strongly in both academia and industry. Motivated by the strong growth in FTL-FM research and the potential impact of FTL-FM on industrial applications, we propose an FTL-FM framework that formulates problems of grounding FMs in the federated learning setting, construct a detailed taxonomy based on the FTL-FM framework to categorize state-of-the-art FTL-FM works, and comprehensively overview FTL-FM works based on the proposed taxonomy. We also establish correspondences between FTL-FM and conventional phases of adapting FM so that FM practitioners can align their research works with FTL-FM. In addition, we overview advanced efficiency-improving and privacy-preserving techniques because efficiency and privacy are critical concerns in FTL-FM. Last, we discuss opportunities and future research directions of FTL-FM. ( 3 min )

Open

Implementing Gradient Descent in PyTorch

The gradient descent algorithm is one of the most popular techniques for training deep neural networks. It has many applications in fields such as computer vision, speech recognition, and natural language processing. While the idea of gradient descent has been around for decades, it’s only recently that it’s been applied to applications related to deep […] The post Implementing Gradient Descent in PyTorch appeared first on MachineLearningMastery.com. ( 25 min )

Open

Training a Linear Regression Model in PyTorch

Linear regression is a simple yet powerful technique for predicting the values of variables based on other variables. It is often used for modeling relationships between two or more continuous variables, such as the relationship between income and age, or the relationship between weight and height. Likewise, linear regression can be used to predict continuous […] The post Training a Linear Regression Model in PyTorch appeared first on MachineLearningMastery.com. ( 24 min )

Making Linear Predictions in PyTorch

Linear regression is a statistical technique for estimating the relationship between two variables. A simple example of linear regression is to predict the height of someone based on the square root of the person’s weight (that’s what BMI is based on). To do this, we need to find the slope and intercept of the line. […] The post Making Linear Predictions in PyTorch appeared first on MachineLearningMastery.com. ( 21 min )

Open

Loading and Providing Datasets in PyTorch

Structuring the data pipeline in a way that it can be effortlessly linked to your deep learning model is an important aspect of any deep learning-based system. PyTorch packs everything to do just that. While in the previous tutorial, we used simple datasets, we’ll need to work with larger datasets in real world scenarios in […] The post Loading and Providing Datasets in PyTorch appeared first on MachineLearningMastery.com. ( 20 min )

Open

Using Dataset Classes in PyTorch

In machine learning and deep learning problems, a lot of effort goes into preparing the data. Data is usually messy and needs to be preprocessed before it can be used for training a model. If the data is not prepared correctly, the model won’t be able to generalize well. Some of the common steps required […] The post Using Dataset Classes in PyTorch appeared first on MachineLearningMastery.com. ( 21 min )

Open

Calculating Derivatives in PyTorch

Derivatives are one of the most fundamental concepts in calculus. They describe how changes in the variable inputs affect the function outputs. The objective of this article is to provide a high-level introduction to calculating derivatives in PyTorch for those who are new to the framework. PyTorch offers a convenient way to calculate derivatives for […] The post Calculating Derivatives in PyTorch appeared first on Machine Learning Mastery. ( 20 min )

Open

Two-Dimensional Tensors in Pytorch

Two-dimensional tensors are analogous to two-dimensional metrics. Like a two-dimensional metric, a two-dimensional tensor also has $n$ number of rows and columns. Let’s take a gray-scale image as an example, which is a two-dimensional matrix of numeric values, commonly known as pixels. Ranging from ‘0’ to ‘255’, each number represents a pixel intensity value. Here, […] The post Two-Dimensional Tensors in Pytorch appeared first on Machine Learning Mastery. ( 21 min )

Open

One-Dimensional Tensors in Pytorch

PyTorch is an open-source deep learning framework based on Python language. It allows you to build, train, and deploy deep learning models, offering a lot of versatility and efficiency. PyTorch is primarily focused on tensor operations while a tensor can be a number, matrix, or a multi-dimensional array. In this tutorial, we will perform some […] The post One-Dimensional Tensors in Pytorch appeared first on Machine Learning Mastery. ( 22 min )

Open

365 Data Science courses free until November 21

Sponsored Post The unlimited access initiative presents a risk-free way to break into data science. The online educational platform 365 Data Science launches the #21DaysFREE campaign and provides 100% free unlimited access to all content for three weeks. From November 1 to 21, you can take courses from renowned instructors and earn […] The post 365 Data Science courses free until November 21 appeared first on Machine Learning Mastery. ( 15 min )

Open

Attend the Data Science Symposium 2022, November 8 in Cincinnati

Sponsored Post Attend the Data Science Symposium 2022 on November 8 The Center for Business Analytics at the University of Cincinnati will present its annual Data Science Symposium 2022 on November 8. This all day in-person event will have three featured speakers and two tech talk tracks with four concurrent presentations in each track. The […] The post Attend the Data Science Symposium 2022, November 8 in Cincinnati appeared first on Machine Learning Mastery. ( 10 min )

Open

My family's unlikely homeschooling journey

My husband Jeremy and I never intended to homeschool, and yet we have now, unexpectedly, committed to homeschooling long-term. Prior to the pandemic, we both worked full-time in careers that we loved and found meaningful, and we sent our daughter to a full-day Montessori school. Although I struggled with significant health issues, I felt unbelievably lucky and fulfilled in both my family life and my professional life. The pandemic upended my careful balance. Every family is different, with different needs, circumstances, and constraints, and what works for one may not work for others. My intention here is primarily to share the journey of my own (very privileged) family. Our unplanned introduction to homeschooling For the first year of the pandemic, most schools in California, where … ( 7 min )

Open

The Jupyter+git problem is now solved

Jupyter notebooks don’t work with git by default. With nbdev2, the Jupyter+git problem has been totally solved. It provides a set of hooks which provide clean git diffs, solve most git conflicts automatically, and ensure that any remaining conflicts can be resolved entirely within the standard Jupyter notebook environment. To get started, follow the directions on Git-friendly Jupyter. Contents The Jupyter+git problem The solution The nbdev2 git merge driver The nbdev2 Jupyter save hook Background The result Postscript: other Jupyter+git tools ReviewNB An alternative solution: Jupytext nbdime The Jupyter+git problem Jupyter notebooks are a powerful tool for scientists, engineers, technical writers, students, teachers, and more. They provide an ideal notebook environment for interact… ( 7 min )